© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 47983
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     url
    0.38
     windows
    0.37
     artikkel
    0.37
     microsoft
    0.36
     Microsoft
    0.36
     "
    0.35
     atas
    0.35
    Windows
    0.34
     bilder
    0.34
    articolo
    0.33
    POSITIVE LOGITS
     सत
    0.38
    Travis
    0.37
    odhana
    0.37
    嘻
    0.37
    丆
    0.37
    ថ្
    0.35
    ოლ
    0.35
    শাল
    0.35
    ندوق
    0.34
     newVal
    0.34
    Activations Density 0.000%

    No Known Activations